Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security

• URL: http://arxiv.org/abs/2510.06525v1
• Date: Tue, 07 Oct 2025 23:53:41 GMT
• Title: Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
• Abstract summary: We show that rank manipulation in text-to-image leaderboards is easier than previously recognized.<n>Our results indicate that rank manipulation in text-to-image leaderboards is easier than previously recognized.
• Score: 24.40199910521865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an attacker must first deanonymize the models behind displayed outputs -- a threat previously demonstrated and explored for large language models (LLMs). We show that this problem can be even more severe for text-to-image leaderboards, where deanonymization is markedly easier. Using over 150,000 generated images from 280 prompts and 19 diverse models spanning multiple organizations, architectures, and sizes, we demonstrate that simple real-time classification in CLIP embedding space identifies the generating model with high accuracy, even without prompt control or historical data. We further introduce a prompt-level separability metric and identify prompts that enable near-perfect deanonymization. Our results indicate that rank manipulation in text-to-image leaderboards is easier than previously recognized, underscoring the need for stronger defenses.

Related papers

• Can Vision-Language Models Reason about AI Edits in Images? [78.04125956307838]
  Vision-Language Models (VLMs) offer a promising alternative due to their strong visual understanding and reasoning capabilities.<n>We propose a GRPO-based training framework that utilizes simple accuracy and format rewards.<n>Our approach achieves competitive detection and localization performance compared to state-of-the-art image forgery detectors.
  arXiv  Detail & Related papers  (2026-07-30T16:23:40Z)
• Identifying Models Behind Text-to-Image Leaderboards [24.40199910521865]
  Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online.<n>In this work, we show that such anonymity can be easily broken.<n>We find that generations from each T2I model form distinctive clusters in the image embedding space, enabling accurate deanonymization without prompt control or training data.
  arXiv  Detail & Related papers  (2026-01-14T17:30:58Z)
• Towards Mechanistic Defenses Against Typographic Attacks in CLIP [23.69564867168339]
  We analyze how CLIP vision encoders behave under typographic attacks.<n>We introduce a method to defend CLIP models against typographic attacks by selectively ablating a typographic circuit.<n>We release a family of dyslexic CLIP models which are significantly more robust against typographic attacks.
  arXiv  Detail & Related papers  (2025-08-28T09:08:30Z)
• ICAS: Detecting Training Data from Autoregressive Image Generative Models [38.1625974271413]
  Training data detection has emerged as a critical task for identifying unauthorized data usage in model training.<n>We conduct the first study applying membership inference to this domain.<n>Our approach exhibits strong robustness and generalization under various data transformations.
  arXiv  Detail & Related papers  (2025-07-07T14:50:42Z)
• Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation [61.31036260686349]
  We propose a novel prompt optimization framework, designed to rephrase a simple user prompt into a sophisticated prompt to a text-to-image model.<n> Specifically, we employ the large vision language models (LVLMs) as the solver to rewrite the user prompt, and concurrently, employ LVLMs as a reward model to score the aesthetics and alignment of the images generated by the optimized prompt.<n>Instead of laborious human feedback, we exploit the prior knowledge of the LVLM to provide rewards, i.e., AI feedback.
  arXiv  Detail & Related papers  (2025-05-22T15:05:07Z)
• Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning [58.16354555208417]
  PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively.<n>The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors.<n>We present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces.
  arXiv  Detail & Related papers  (2025-05-19T16:35:45Z)
• Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models [111.58315434849047]
  We introduce a novel ranking attack framework named Attack-in-the-Chain.<n>It tracks interactions between large language models (LLMs) and Neural ranking models (NRMs) based on chain-of-thought.<n> Empirical results on two web search benchmarks show the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-12-25T04:03:09Z)
• Memory Backdoor Attacks on Neural Networks [3.2720947374803777]
  We propose the memory backdoor attack, where a model is covertly trained to specific training samples and later selectively output them. We demonstrate the attack on image classifiers, segmentation models, and a large language model (LLM)
  arXiv  Detail & Related papers  (2024-11-21T16:09:16Z)
• Undermining Image and Text Classification Algorithms Using Adversarial Attacks [0.0]
  Our study addresses the gap by training various machine learning models and using GANs and SMOTE to generate additional data points aimed at attacking text classification models. Our experiments reveal a significant vulnerability in classification models. Specifically, we observe a 20 % decrease in accuracy for the top-performing text classification models post-attack, along with a 30 % decrease in facial recognition accuracy.
  arXiv  Detail & Related papers  (2024-11-03T18:44:28Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models [47.03411822627386]
  We propose several problem-specific novel attacks minimizing different metrics in accuracy and mIoU. Surprisingly, existing attempts of adversarial training for semantic segmentation models turn out to be weak or even completely non-robust. We show how recently proposed robust ImageNet backbones can be used to obtain adversarially robust semantic segmentation models with up to six times less training time for PASCAL-VOC and the more challenging ADE20k.
  arXiv  Detail & Related papers  (2023-06-22T14:56:06Z)
• POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models [62.23255433487586]
  We propose an unsupervised fine-tuning framework to fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and target data.
  arXiv  Detail & Related papers  (2023-04-29T22:05:22Z)
• Prefix Conditioning Unifies Language and Label Supervision [84.11127588805138]
  We show that dataset biases negatively affect pre-training by reducing the generalizability of learned representations. In experiments, we show that this simple technique improves the performance in zero-shot image recognition accuracy and robustness to the image-level distribution shift.
  arXiv  Detail & Related papers  (2022-06-02T16:12:26Z)
• Camera-aware Proxies for Unsupervised Person Re-Identification [60.26031011794513]
  This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. We propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera. Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model.
  arXiv  Detail & Related papers  (2020-12-19T12:37:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.